© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2196
    Prev
    Next
    INDEX
    Explanations

    vaccine hesitancy

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is specifically detecting mentions of pediatric vaccination schedules and immunization-related terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     食器
    0.69
     家具
    0.69
    宝石
    0.67
    水位
    0.65
    ócio
    0.65
     уйна
    0.64
     خر
    0.64
    🦐
    0.62
     Explosion
    0.61
     FODC
    0.61
    POSITIVE LOGITS
     vaccination
    2.97
     vaccine
    2.91
     vaccines
    2.80
     vaccinate
    2.66
     vaccinations
    2.64
    疫苗
    2.63
    vacc
    2.61
     Vaccine
    2.61
    Vacc
    2.58
     vaccin
    2.58
    Activations Density 0.186%

    No Known Activations